Objective To modify the YOLOv5 algorithm with similarity attention mechanism(SimAM)to enhance the recognition and segmentation accuracy of CT images for cerebral hemorrhage.Methods A basic framework was established with a YOLOv5 algorithm consisting of a backbone network(Backbone),a neck module(Neck)and a head module(Head),and then SimAM was introduced at the end of Backbone to form a YOLOv5-Sim-B algorithm and at the end of Neck to construct a YOLOv5-Sim-N algorithm.The YOLOv5-Sim-B and YOLOv5-Sim-N algorithms were trained and validated using the CT image dataset for cerebral hemorrhage publicly available on the Kaggle competition platform,and compared with the traditional YOLOv5 algorithm for recognizing and segmenting cerebral hemorrhagic lesions in CT images.Results In case the value of IoU-T was 0.6,the mean average precision(mAP)was 0.967 for YOLOv5-Sim-B algorithm,0.960 for the YOLOv5-Sim-N algorithm and 0.964 for the traditional YOLOv5 algorithm during the recognition and segmentation of cerebral hemorrhagic lesions in CT images.Conclusion The proposed algorithm gains advantages in detection accuracy and robustness,and can efficiently identify and segment cerebral hemorrhage foci in CT images.[Chinese Medical Equipment Journal,2025,46(5):1-8]

AIM To establish an HPLC-MS/MS method for the simultaneous content determination of dehydrodiisoeugenol,eugenol,costiolactone,dehydrocostiolactone,quercetin,isorhamnetin,luteolin,caffeic acid,gallic acid,protocatechuic acid,ellagic acid and kaempferol in Anshen Buxin Liuwei Pills,and to make chemical pattern recognition.METHODS The analysis was performed on a 35 ℃ thermostatic Shim-pack GST-HP C18 column(2.1 mm × 100 mm,3 μm),with the mobile phase comprising of methanol-water(containing 0.1％formic acid)flowing at 0.25 mL/min in a gradient elution manner,and electron spray ionization source was adopted in positive and negative ion scanning with multiple reaction monitoring mode.Subsequently,cluster analysis,principal component analysis and orthogonal partial least square-discriminant analysis were performed.RESULTS Twelve constituents showed good linear relationships within their own ranges(r≥0.999 0),whose average recoveries were 95.38％-105.00％with the RSDs of 1.91％-5.14％.Thirteen batches of samples were clustered into 3 types,ellagic acid,dehydrocodenolactone,dehydrodiisoeugenol,protocatechuic acid,gallic acid,quercetin and kaempferol were taken as potential quality differential markers.CONCLUSION This accurate,sensitive,stable and reproducible method can be used for the quality control and evaluation of Anshen Buxin Liuwei Pills.

Asarum forbesii is a perennial herb born in a shaded and humid environment, which is warm in nature. With the efficacy of warming lung, resolving fluid retention, and relieving coughs, it can be used to treat the syndrome of cold fluid accumulating in lung. To investigate the effects of different shading conditions on the composition and efficacy of A. forbesii, this study planted A. forbesii under 20% natural light(NL20), 40% natural light(NL40), 60% natural light(NL60), and 80% natural light(NL80) and utilized ultra performance liquid chromatography(UPLC) and micro broth 2-fold dilution method to detect the volatile chemical compounds and the minimum inhibitory concentration. At the same time, the study investigated the effects of A. forbesii grown under different shading conditions on the signs, pathological changes of lung tissues, serum cytokine levels, activities of mitochondrial respiratory chain complexes Ⅰ-Ⅴ in lung tissues, and relative expression of related genes of mice with syndrome of cold fluid accumulating in lung. The results indicated that with the increase of shading, the content of kakuol, methyl eugenol, and asarinin in A. forbesii and the antibacterial effect showed a tendency of increasing first and then decreasing, and the NL40 group was significantly better than the other groups. Under the conditions of NL20 and NL40, A. forbesii significantly alleviated the pathological damage to lung tissues, restored the homeostasis of the lung, and enhanced the energy metabolism level of mice with syndrome of cold fluid accumulating in lung. In addition, A. forbesii planted under the two conditions reduced the content of interleukin-8(IL-8), interleukin-13(IL-13), tumor necrosis factor-α(TNF-α), and mucin 5AC(MUC5AC), increased the levels of interleukin-10(IL-10) and aquaporin 1(AQP1), lowered the expression of MMP9, VEGF, TGF-β, and MAPK3. In conclusion, the therapeutic effect of A. forbesii on the syndrome of cold fluid accumulating in lung was positively correlated with the degree of shading, and the chemical composition and efficacy of warming lung and resolving fluid retention were optimal under the conditions of NL20-NL40. This study can provide reference for the pharmacological research and cultivation of A. forbesii.
Animals ; Mice ; Lung/pathology* ; Drugs, Chinese Herbal/administration & dosage* ; Male ; Light ; Cytokines/genetics* ; Humans

Objective To propose an improved YOLOv8 algorithm based on polarized self-attention(PSA)and deformable attention(DAT)so as to enhance the detection of pulmonary nodules in CT images.Methods A basic framework was established with a YOLOv8 model consisting of a backbone network(Backbone),a neck module(Neck)and a head module(Head).PSA was introduced into the end of the spatial pyramid pooling-fast(SPPF)of Backbone to construct a YOLOv8-PSA algorithm,and DAT was involved in the medium-scale feature layer P4 in Head to form a YOLOv8-DAT algorithm.The YOLOv8-PSA and YOLOv8-DAT algorithms were trained and validated using the CT image dataset of pulmonary nodules from public platforms,and compared with the original YOLOv8 algorithm for the detection of pulmonary nodule lesions in CT images.Results When used for pulmonary module detection of CT images,the YOLOv8-DAT algorithm had the mean average precision(mAP)in case of intersection over union threshold of 0.5(mAP50),mAP in case of intersection over union threshold of 0.5 to 0.95(mAP50-95)and precision ratio being 0.918,0.588 and 0.960 respectively,which gained advantages over the YOLOv8-PSA algorithm with mAP50,mAP50-95 and precision ratio being 0.914,0.583 and 0.945 respectively,and over the original YOLOv8 algorithm with mAP50,mAP50-95 and precision ratio being 0.911,0.564 and 0.952 respectively.Conclusion The YOLOv8-DAT algorithm detects pulmonary modules in CT images effectively,and facilitates early screening and diagnosis of pulmonary modules clinically.[Chinese Medical Equipment Journal,2025,46(8):1-10]

AIM To establish an HPLC-MS/MS method for the simultaneous content determination of dehydrodiisoeugenol,eugenol,costiolactone,dehydrocostiolactone,quercetin,isorhamnetin,luteolin,caffeic acid,gallic acid,protocatechuic acid,ellagic acid and kaempferol in Anshen Buxin Liuwei Pills,and to make chemical pattern recognition.METHODS The analysis was performed on a 35 ℃ thermostatic Shim-pack GST-HP C18 column(2.1 mm × 100 mm,3 μm),with the mobile phase comprising of methanol-water(containing 0.1％formic acid)flowing at 0.25 mL/min in a gradient elution manner,and electron spray ionization source was adopted in positive and negative ion scanning with multiple reaction monitoring mode.Subsequently,cluster analysis,principal component analysis and orthogonal partial least square-discriminant analysis were performed.RESULTS Twelve constituents showed good linear relationships within their own ranges(r≥0.999 0),whose average recoveries were 95.38％-105.00％with the RSDs of 1.91％-5.14％.Thirteen batches of samples were clustered into 3 types,ellagic acid,dehydrocodenolactone,dehydrodiisoeugenol,protocatechuic acid,gallic acid,quercetin and kaempferol were taken as potential quality differential markers.CONCLUSION This accurate,sensitive,stable and reproducible method can be used for the quality control and evaluation of Anshen Buxin Liuwei Pills.

An assay was established for detection of toxigenic Clostridioides difficile by combining microfluidic chip analysis with immunochromatography,and its performance was evaluated and compared with those of the Xpert C.difficile/Epi and VIDAS CD AB tests.Primer pairs were designed according to the tcdB and tpi genes in C.difficile.The specificity,limit of detection,reproducibility,and stability were evaluated.A total of 215 stool samples from patients with diarrhea were collected and tested in parallel with the Xpert C.difficile/Epi,VIDAS CDAB,and our assay.C.difficile was isolated from samples,and the tcdB gene was identified when discrepant results were obtained from the three above assays.Our assay showed no cross-reaction with other diarrhea-associated pathogens.Its reproducibility was 100％in testing of two standard plasmids containing tcdB and tpi genes at two concentrations(105 and 102 copies/μL).Two standard plasmids were detected after the PCR and immunochromatography reagents had been stored for 3,6,9,and 12 months,and all the results were posi-tive.The limit of detection was 10 copies/μL for toxigenic C.difficile.Testing of 33 samples positive for C.difficile with our assay(33/215,15.3％)yielded findings statistically coherent with those of the Xpert C.difficile/Epi test(kappa value=0.965).The sensitivity,specificity,positive predictive value,and negative predictive value of our assay,with respect to Xpert C.difficile/Epi as the standard,were 94.3％,100.0％,100.0％,and 98.9％;these values were significantly higher than those of VIDAS CDAB(60.0％,98.9％,91.3％,and 92.7％)(Kappa=0.714,OR=157.50,95％CI:62.03-847.28,P=0.013).In conclusion,our newly developed assay is specific,stable,and reproducible,and may be used for rapid and accu-rate detection of toxigenic C.difficile.The assay could be used for C.difficile infection screening in outpatient and emergen-cy,community medical service center,and epidemiological settings.

Objective To modify the YOLOv5 algorithm with similarity attention mechanism(SimAM)to enhance the recognition and segmentation accuracy of CT images for cerebral hemorrhage.Methods A basic framework was established with a YOLOv5 algorithm consisting of a backbone network(Backbone),a neck module(Neck)and a head module(Head),and then SimAM was introduced at the end of Backbone to form a YOLOv5-Sim-B algorithm and at the end of Neck to construct a YOLOv5-Sim-N algorithm.The YOLOv5-Sim-B and YOLOv5-Sim-N algorithms were trained and validated using the CT image dataset for cerebral hemorrhage publicly available on the Kaggle competition platform,and compared with the traditional YOLOv5 algorithm for recognizing and segmenting cerebral hemorrhagic lesions in CT images.Results In case the value of IoU-T was 0.6,the mean average precision(mAP)was 0.967 for YOLOv5-Sim-B algorithm,0.960 for the YOLOv5-Sim-N algorithm and 0.964 for the traditional YOLOv5 algorithm during the recognition and segmentation of cerebral hemorrhagic lesions in CT images.Conclusion The proposed algorithm gains advantages in detection accuracy and robustness,and can efficiently identify and segment cerebral hemorrhage foci in CT images.[Chinese Medical Equipment Journal,2025,46(5):1-8]

Objective To propose an improved YOLOv8 algorithm based on polarized self-attention(PSA)and deformable attention(DAT)so as to enhance the detection of pulmonary nodules in CT images.Methods A basic framework was established with a YOLOv8 model consisting of a backbone network(Backbone),a neck module(Neck)and a head module(Head).PSA was introduced into the end of the spatial pyramid pooling-fast(SPPF)of Backbone to construct a YOLOv8-PSA algorithm,and DAT was involved in the medium-scale feature layer P4 in Head to form a YOLOv8-DAT algorithm.The YOLOv8-PSA and YOLOv8-DAT algorithms were trained and validated using the CT image dataset of pulmonary nodules from public platforms,and compared with the original YOLOv8 algorithm for the detection of pulmonary nodule lesions in CT images.Results When used for pulmonary module detection of CT images,the YOLOv8-DAT algorithm had the mean average precision(mAP)in case of intersection over union threshold of 0.5(mAP50),mAP in case of intersection over union threshold of 0.5 to 0.95(mAP50-95)and precision ratio being 0.918,0.588 and 0.960 respectively,which gained advantages over the YOLOv8-PSA algorithm with mAP50,mAP50-95 and precision ratio being 0.914,0.583 and 0.945 respectively,and over the original YOLOv8 algorithm with mAP50,mAP50-95 and precision ratio being 0.911,0.564 and 0.952 respectively.Conclusion The YOLOv8-DAT algorithm detects pulmonary modules in CT images effectively,and facilitates early screening and diagnosis of pulmonary modules clinically.[Chinese Medical Equipment Journal,2025,46(8):1-10]

Objective To establish a stable,reliable,and clinically relevant porcine model of endotoxin-induced acute respiratory distress syndrome(ARDS).Methods Ten 8-month-old male Bama minipigs were deeply sedated,followed by invasive mechanical ventilation and electrocardiographic monitoring.Lipopolysaccharide(LPS)was intravenously pumped at 600 μg/(kg·h)for 3 hours,then maintained at 15 μg/(kg·h)thereafter.Dynamic monitoring was performed at five time points after LPS injection(LPS 0,1,3,5,and 8 h),including arterial blood gas analysis and chest computed tomography(CT)scans.Pathological examination of lung tissues obtained via bronchoscopic biopsy(HE staining and transmission electron microscopy)was conducted.These indicators were comprehensively used to evaluate the success of the animal model.Results At 5 hours after LPS administration,8 minipigs developed symptoms such as skin cyanosis,elevated body temperature,and respiratory distress.The oxygenation index decreased to<300 mmHg.Chest CT scans showed diffuse pulmonary infiltrates.Histopathology revealed alveolar edema and hyaline membrane formation.Transmission electron microscopy demonstrated disruption of pulmonary blood-air barrier,depletion of lamellar bodies in type Ⅱ pneumocytes,inflammatory cell infiltration,and exudation of plasma proteins and fibrin.Compared with LPS 0 h,at LPS 8 h,the oxygenation index and arterial blood pH were significantly decreased(P<0.001),while blood lactic acid and serum potassium were significantly increased(P<0.05);serum calcium and base excess were significantly decreased(P<0.05),and the lung injury score based on HE-stained lung sections was significantly increased(P<0.01).Conclusion The porcine ARDS model established by continuous LPS injection can dynamically simulate the pathophysiological characteristics and typical pathological manifestations of clinical septic ARDS,making it an effective tool to study the pathogenesis,prevention,and treatment strategies of septic ARDS.

With the rapid development of deep learning(DL)technology,its potential applications in the medical field have become increasingly prominent.As a refractory disease,osteonecrosis of the femoral head(ONFH)has certain limitations in traditional diagnostic and therapeutic approaches.The application of DL technology is expected to overcome these limitations and improve diagnosis and treatment outcomes.At present,the applications of DL models-including enhancing image clarity,improving diagnostic accuracy and efficiency,conducting prognostic evaluations,optimizing preoperative planning,assisting intraoperative imaging,and customizing personalized treatment plans-have fully demonstrated their tremendous potential in the diagnosis and treatment of ONFH.This review summarizes the current application status of DL in ONFH diagnosis and treatment,aiming to provide references and insights for future related research.